Skip to content

Sleep Detection Demo

A demo is provided to showcase the capabilities of the sleep detect model. Similar to other modes, the demo can be invoked either via CLI or within sleepkit python package. At a high level, the demo performs the following actions based on the provided configuration parameters:

  1. Load the configuration file (e.g. demo.json)
  2. Load the desired dataset features (e.g. fs004)
  3. Load the trained model (e.g. sleep-detect)
  4. Load random test subject's data
  5. Perform inference either on PC or EVB
  6. Generate report

Usage

PC backend

  1. Create / modify configuration file (e.g. demo.json)
  2. Ensure "pc" is selected as the backend in configuration file.
  3. Run demo sleepkit --mode demo --task detect --config ./configs/sleep-detect/demo.json
  4. HTML report will be saved to ${job_dir}/report.html

EVB backend

  1. Create / modify configuration file (e.g. demo.json)
  2. Ensure "evb" is selected as the backend in configuration file.
  3. Plug EVB into PC via two USB-C cables.
  4. Build and flash firmware to EVB cd evb && make && make deploy
  5. Run demo sleepkit --mode demo --task detect --config ./configs/sleep-detect/demo.json
  6. HTML report will be saved to ${job_dir}/report.html

Outputs